luongnv89/blog-draft

开发者: luongnv89许可证: MIT46.4k

Test a learner on a single Claude Code tutorial lesson (01-10) with 10 questions, scoring answers and flagging weak spots. Use before, during, or after a lesson. Don't use for whole-tutorial assessment or explaining a topic instead of testing it.

关于Skill 介绍README常见问题

典型用途

只靠通用对话时，根据想法和资源起草博客文章。当用户想要撰写博客文章、从研究中创建内容或起草文章时使用。指导用户进…这件事容易做得散，结果也不稳定。

blog-draft把这件事收成可复用的技能。Agent 被点到时按这个目标组织步骤，输入侧常见的是文本，交付侧常见的是文本。它不替代你读仓库里的 SKILL.md，只帮你在安装前判断这件事值不值得交给 Agent。

何时会触发

当用户的说法接近这项技能的名称或任务时会匹配。用户用名称或接近的说法点名这项技能，或描述与它相同的任务。

请用blog-draft处理这件事
帮我做一次Agent 技能
按blog-draft的方式完成，不要换一套通用步骤

若用户只是随口提到相关词、并不要求现在就做，未必应该触发。具体匹配句子以 GitHub 上的 SKILL.md 为准。

安装前注意

安装前先看它会动哪些材料：当前能确定的输入是文本，输出是文本。是否会改文件、跑命令或访问网络，仓库说明里没有写死，不能从名称推断。

权限、副作用和适用范围都以该仓库的 SKILL.md 为准。涉及生产数据、账号或对外发布时，先在小范围试一次，再决定是否常用。

重要提示：本站仅作 Skill 资源导航与收录，正文以 GitHub 原仓库为准，版权归原项目所有。

文件

索引更新于 11/2/2026, 10:18:37 AM

.claude/skills/lesson-quiz/README.md2.4 KB在 GitHub 查看 ↗

.claude/skills/lesson-quiz/SKILL.md9.1 KB当前在 GitHub 查看 ↗

.claude/skills/lesson-quiz/references/question-bank.md59.3 KB在 GitHub 查看 ↗

.claude/skills/lesson-quiz/references/results-template.md2.1 KB在 GitHub 查看 ↗

Lesson Quiz

Interactive quiz that tests understanding of a specific Claude Code lesson with 10 questions, provides per-question feedback, and identifies areas to review.

Prerequisites

This skill requires:

The tutorial repo checked out, so the lesson directories 01-slash-commands/ … 10-cli/ and each README.md are readable.
references/question-bank.md present in this skill (the source of all questions).

Before starting, confirm the target lesson's README.md exists. If it is missing, do not fabricate questions — warn the user and ask them to check the repository structure (see Error Handling).

Guardrails:

Never invent questions or answers. Ask only questions drawn from references/question-bank.md for the selected lesson; if the bank lacks entries for a lesson, say so rather than making them up.
Score accurately. Track which shuffled position holds the correct answer for every question and validate each response against it — never guess a score.
Confirm timing before scoring. The pre/during/after choice changes how results are framed; do not skip it.

Instructions

Step 1: Determine the Lesson

If the user provided a lesson as an argument (e.g., /lesson-quiz hooks or /lesson-quiz 03), map it to the lesson directory:

Lesson mapping:

01, slash-commands, commands → 01-slash-commands
02, memory → 02-memory
03, skills → 03-skills
04, subagents, agents → 04-subagents
05, mcp → 05-mcp
06, hooks → 06-hooks
07, plugins → 07-plugins
08, checkpoints, checkpoint → 08-checkpoints
09, advanced, advanced-features → 09-advanced-features
10, cli → 10-cli

If no argument was provided, present a selection prompt using AskUserQuestion:

Question 1 (header: "Lesson"): "Which lesson do you want to quiz on?" Options:

"Slash Commands (01)" — Custom commands, skills, frontmatter, arguments
"Memory (02)" — CLAUDE.md, memory hierarchy, rules, auto memory
"Skills (03)" — Progressive disclosure, auto-invocation, SKILL.md
"Subagents (04)" — Task delegation, agent config, isolation

Question 2 (header: "Lesson"): "Which lesson do you want to quiz on? (continued)" Options:

"MCP (05)" — External integration, transport, servers, tool search
"Hooks (06)" — Event automation, PreToolUse, exit codes, JSON I/O
"Plugins (07)" — Bundled solutions, marketplace, plugin.json
"More lessons..." — Checkpoints, Advanced Features, CLI

If "More lessons..." is selected, present:

Question 3 (header: "Lesson"): "Select your lesson:" Options:

"Checkpoints (08)" — Rewind, restore, safe experimentation
"Advanced Features (09)" — Planning, permissions, print mode, thinking
"CLI Reference (10)" — Flags, output formats, scripting, piping

Step 2: Read the Lesson Content

Read the lesson README.md file to refresh context:

Read file: <lesson-directory>/README.md

Then use the question bank from references/question-bank.md for that lesson (10 pre-written questions with answers and explanations). To stay within the context budget, read only the one selected lesson's README — not all ten.

Step 3: Present the Quiz

Ask the user about quiz timing context:

Use AskUserQuestion (header: "Timing"): "When are you taking this quiz relative to the lesson?" Options:

"Before (pre-test)" — I haven't read the lesson yet, testing my prior knowledge
"During (progress check)" — I'm partway through the lesson
"After (mastery check)" — I've completed the lesson and want to verify understanding

This context affects how the results are framed (see Step 5).

Step 4: Present Questions in Rounds

Present 10 questions from the question bank in rounds of 2 questions each (5 rounds total). Each question uses AskUserQuestion with the question text and 3-4 answer options.

IMPORTANT: Use AskUserQuestion with max 4 options per question, 2 questions per round.

For each round, present 2 questions. After the user answers each round, immediately show per-question feedback: whether each answer was correct or incorrect, and if incorrect, show the correct answer and a brief explanation. Then proceed to the next round. After all 5 rounds, proceed to final scoring.

Question format per round:

Each question from the question bank has:

question: The question text
options: 3-4 answer choices (one correct, labeled in the bank)
correct: The correct answer label
explanation: Why the answer is correct
category: "conceptual" or "practical"

CRITICAL — Shuffle answer options: For each question, you MUST randomize the order of the answer options before presenting them via AskUserQuestion. Do NOT present them in the order they appear in the question bank (A, B, C, D), and do NOT place the correct answer first. Use a different random permutation for each question. Track which shuffled position contains the correct answer so you can score accurately.

Example: If the question bank lists options A (correct), B, C, D — you might present them as: C, A, D, B. The correct answer is now in position 2.

Present each question using AskUserQuestion. Record the user's answer for each.

Step 5: Score and Present Results

After all rounds, calculate the score and present results.

Scoring:

Each correct answer = 1 point
Total possible = 10 points

Grade scale:

9-10: Mastered — Excellent understanding
7-8: Proficient — Good grasp, minor gaps
5-6: Developing — Fundamentals understood, needs review
3-4: Beginning — Significant gaps, review recommended
0-2: Not yet — Start from the beginning of this lesson

Output format: Follow the report template in references/results-template.md. It defines the score line, the per-question results table, the "Incorrect Answers — Review These" block, the timing-specific message (pre-test / during / after), and the "Recommended Next Steps" section. Fill its bracketed placeholders with this run's data.

Step 6: Offer Follow-up

After presenting results, use AskUserQuestion:

"What would you like to do next?" Options:

"Retake this quiz" — Try the same lesson quiz again
"Quiz another lesson" — Switch to a different lesson
"Explain a topic I missed" — Get a detailed explanation of an incorrect answer
"Done" — End the quiz session

If Retake: Go back to Step 4 (skip timing question, use same timing). If Quiz another lesson: Go back to Step 1. If Explain a topic: Ask which question number, then read the relevant section from the lesson README.md and explain it with examples.

Acceptance Criteria

A completed quiz run must satisfy all of these — verify each before presenting final results:

Exactly one lesson (01-10) was resolved before any question was asked.
The timing context (before / during / after) was captured via AskUserQuestion.
10 questions from references/question-bank.md for that lesson were presented, in 5 rounds of 2, with answer options shuffled per question.
Every answer was scored against the tracked correct-position, producing an integer score in the range 0-10.
Expected output: a ## Lesson Quiz Results report containing the score line (Score: N/10 with a grade label), the per-question results table, an "Incorrect Answers — Review These" block for each miss, and a timing-specific message.
The follow-up prompt (retake / another lesson / explain / done) was offered.

Example: for a 7/10 "after" run on Hooks, the report asserts Score: 7/10 — Proficient, lists all 10 rows in the results table, and expands the 3 incorrect questions with correct answer, explanation, and a review pointer.

Edge Cases & Error Handling

Invalid lesson argument

If the argument doesn't match any lesson, show the valid lesson list and ask the user to pick one.

User wants to quit mid-quiz

If the user indicates they want to stop during any round, present partial results for the questions answered so far (score out of the number attempted, not out of 10).

Lesson README not found

If the README.md file doesn't exist at the expected path, inform the user and suggest checking the repository structure. Do not proceed with fabricated content.

Question bank missing entries for a lesson

If references/question-bank.md has no questions for the resolved lesson, tell the user and stop — never invent questions to fill the gap.

Validation

Triggering test suite

Should trigger:

"quiz me on hooks"
"lesson quiz"
"test my knowledge of lesson 3"
"practice quiz for MCP"
"do I understand skills"
"quiz me on slash commands"
"lesson-quiz 06"
"test me on checkpoints"
"how well do I know the CLI"
"quiz me before I start the memory lesson"

Should NOT trigger:

"assess my overall level" (use /self-assessment)
"explain hooks to me"
"create a hook"
"what is MCP"
"review my code"

重要提示：本站仅作 Skill 资源导航与收录，正文以 GitHub 原仓库为准，版权归原项目所有。

🌐 Language / Ngôn ngữ / 语言 / Мова: English | Tiếng Việt | 中文 | Українська | 日本語

Master Claude Code in a Weekend

Go from typing claude to orchestrating agents, hooks, skills, and MCP servers — with visual tutorials, copy-paste templates, and a guided learning path.

Get Started in 15 Minutes | Find Your Level | Browse the Feature Catalog

The Problem
How Claude How To Fixes This
How It Works
Not Sure Where to Start?
Get Started in 15 Minutes
What Can You Build With This?
FAQ
Contributing
License

The Problem

You installed Claude Code. You ran a few prompts. Now what?

The official docs describe features — but don't show you how to combine them. You know slash commands exist, but not how to chain them with hooks, memory, and subagents into a workflow that actually saves hours.
There's no clear learning path. Should you learn MCP before hooks? Skills before subagents? You end up skimming everything and mastering nothing.
Examples are too basic. A "hello world" slash command doesn't help you build a production code review pipeline that uses memory, delegates to specialized agents, and runs security scans automatically.

You're leaving 90% of Claude Code's power on the table — and you don't know what you don't know.

How Claude How To Fixes This

This isn't another feature reference. It's a structured, visual, example-driven guide that teaches you to use every Claude Code feature with real-world templates you can copy into your project today.

	Official Docs	This Guide
Format	Reference documentation	Visual tutorials with Mermaid diagrams
Depth	Feature descriptions	How it works under the hood
Examples	Basic snippets	Production-ready templates you use immediately
Structure	Feature-organized	Progressive learning path (beginner to advanced)
Onboarding	Self-directed	Guided roadmap with time estimates
Self-Assessment	None	Interactive quizzes to find your gaps and build a personalized path

What you get:

10 tutorial modules covering every Claude Code feature — from slash commands to custom agent teams
Copy-paste configs — slash commands, CLAUDE.md templates, hook scripts, MCP configs, subagent definitions, and full plugin bundles
Mermaid diagrams showing how each feature works internally, so you understand why, not just how
A guided learning path that takes you from beginner to power user in 11-13 hours
Built-in self-assessment — run /self-assessment or /lesson-quiz hooks directly in Claude Code to identify gaps

Start the Learning Path ->

How It Works

1. Find your level

Take the self-assessment quiz or run /self-assessment in Claude Code. Get a personalized roadmap based on what you already know.

2. Follow the guided path

Work through 10 modules in order — each builds on the last. Copy templates directly into your project as you learn.

3. Combine features into workflows

The real power is in combining features. Learn to wire slash commands + memory + subagents + hooks into automated pipelines that handle code reviews, deployments, and documentation generation.

4. Test your understanding

Run /lesson-quiz [topic] after each module. The quiz pinpoints what you missed so you can fill gaps fast.

Get Started in 15 Minutes

Trusted by Developers

GitHub stars from developers who use Claude Code daily
Forks from teams adapting this guide for their own workflows
Actively maintained — synced with every Claude Code release (latest: v2.1.310, October 2026)
Community-driven — contributions from developers who share their real-world configurations

Not Sure Where to Start?

Take the self-assessment or pick your level:

Level	You can...	Start here	Time
Beginner	Start Claude Code and chat	Slash Commands	~2.5 hours
Intermediate	Use CLAUDE.md and custom commands	Skills	~3.5 hours
Advanced	Configure MCP servers and hooks	Advanced Features	~5 hours

Full learning path with all 10 modules:

Order	Module	Level	Time
1	Slash Commands	Beginner	30 min
2	Memory	Beginner+	45 min
3	Checkpoints	Intermediate	45 min
4	CLI Basics	Beginner+	30 min
5	Skills	Intermediate	1 hour
6	Hooks	Intermediate	1 hour
7	MCP	Intermediate+	1 hour
8	Subagents	Intermediate+	1.5 hours
9	Advanced Features	Advanced	2-3 hours
10	Plugins	Advanced	2 hours

Complete Learning Roadmap ->

Get Started in 15 Minutes

Installation note: Starting in v2.1.113, Claude Code ships as a native per-platform binary (macOS/Linux/Windows). The recommended install is the native installer (curl -fsSL https://claude.ai/install.sh | bash); npm installation is deprecated in the official README; prefer the native installer, Homebrew (brew install --cask claude-code) or WinGet (winget install Anthropic.ClaudeCode). For reference, npm install -g @anthropic-ai/claude-code pulls the same native binary through a per-platform optional dependency at install time. As of v2.1.116, downloads come from https://downloads.claude.ai/claude-code-releases — corporate proxies must allowlist this host.

# 1. Clone the guide
git clone https://github.com/luongnv89/claude-howto.git
cd claude-howto

# 2. Copy your first slash command
mkdir -p /path/to/your-project/.claude/commands
cp 01-slash-commands/optimize.md /path/to/your-project/.claude/commands/

# 3. Try it — in Claude Code, type:
# /optimize

# 4. Ready for more? Set up project memory:
cp 02-memory/project-CLAUDE.md /path/to/your-project/CLAUDE.md

# 5. Install a skill:
cp -r 03-skills/code-review-specialist ~/.claude/skills/

Want the full setup? Here's the 1-hour essential setup:

# Slash commands (15 min)
cp 01-slash-commands/*.md .claude/commands/

# Project memory (15 min)
cp 02-memory/project-CLAUDE.md ./CLAUDE.md

# Install a skill (15 min)
cp -r 03-skills/code-review-specialist ~/.claude/skills/

# Weekend goal: add hooks, subagents, MCP, and plugins
# Follow the learning path for guided setup

View the Full Installation Reference

What Can You Build With This?

Use Case	Features You'll Combine
Automated Code Review	Slash Commands + Subagents + Memory + MCP
Team Onboarding	Memory + Slash Commands + Plugins
CI/CD Automation	CLI Reference + Hooks + Background Tasks
Documentation Generation	Skills + Subagents + Plugins
Security Audits	Subagents + Skills + Hooks (read-only mode)
DevOps Pipelines	Plugins + MCP + Hooks + Background Tasks
Complex Refactoring	Checkpoints + Planning Mode + Hooks

FAQ

Is this free? Yes. MIT licensed, free forever. Use it in personal projects, at work, in your team — no restrictions beyond including the license notice.

Is this maintained? Actively. The guide is synced with every Claude Code release. Current version: v2.1.310 (October 2026), compatible with Claude Code 2.1+.

How is this different from the official docs? The official docs are a feature reference. This guide is a tutorial with diagrams, production-ready templates, and a progressive learning path. They complement each other — start here to learn, reference the docs when you need specifics.

How long does it take to go through everything? 11-13 hours for the full path. But you'll get immediate value in 15 minutes — just copy a slash command template and try it.

Can I use this with Claude Sonnet / Haiku / Opus? Yes. All templates work with Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 5.5, and Claude Haiku 4.5.

Can I contribute? Absolutely. See CONTRIBUTING.md for guidelines. We welcome new examples, bug fixes, documentation improvements, and community templates.

Can I read this offline? Yes. Run uv run scripts/build_epub.py to generate an EPUB ebook with all content and rendered diagrams.

Start Mastering Claude Code Today

You already have Claude Code installed. The only thing between you and 10x productivity is knowing how to use it. This guide gives you the structured path, the visual explanations, and the copy-paste templates to get there.

MIT licensed. Free forever. Clone it, fork it, make it yours.

Start the Learning Path -> | Browse the Feature Catalog | Get Started in 15 Minutes

Quick Navigation — All Features

Feature	Description	Folder
Feature Catalog	Complete reference with installation commands	CATALOG.md
Slash Commands	User-invoked shortcuts	01-slash-commands/
Memory	Persistent context	02-memory/
Skills	Reusable capabilities	03-skills/
Subagents	Specialized AI assistants	04-subagents/
MCP Protocol	External tool access	05-mcp/
Hooks	Event-driven automation	06-hooks/
Plugins	Bundled features	07-plugins/
Checkpoints	Session snapshots & rewind	08-checkpoints/
Advanced Features	Planning, thinking, background tasks	09-advanced-features/
CLI Reference	Commands, flags, and options	10-cli/
Blog Posts	Real-world usage examples	Blog Posts

Feature Comparison

Feature	Invocation	Persistence	Best For
Slash Commands	Manual (`/cmd`)	Session only	Quick shortcuts
Memory	Auto-loaded	Cross-session	Long-term learning
Skills	Auto-invoked	Filesystem	Automated workflows
Subagents	Auto-delegated	Isolated context	Task distribution
MCP Protocol	Auto-queried	Real-time	Live data access
Hooks	Event-triggered	Configured	Automation & validation
Plugins	One command	All features	Complete solutions
Checkpoints	Manual/Auto	Session-based	Safe experimentation
Planning Mode	Manual/Auto	Plan phase	Complex implementations
Background Tasks	Manual	Task duration	Long-running operations
CLI Reference	Terminal commands	Session/Script	Automation & scripting

Installation Quick Reference

# Slash Commands
cp 01-slash-commands/*.md .claude/commands/

# Memory
cp 02-memory/project-CLAUDE.md ./CLAUDE.md

# Skills
cp -r 03-skills/code-review-specialist ~/.claude/skills/

# Subagents
cp 04-subagents/*.md .claude/agents/

# MCP
claude mcp add --transport http github https://api.githubcopilot.com/mcp/ --header "Authorization: Bearer YOUR_GITHUB_PAT"

# Hooks
mkdir -p ~/.claude/hooks
cp 06-hooks/*.sh ~/.claude/hooks/
chmod +x ~/.claude/hooks/*.sh

# Plugins (load a local plugin from the repo root)
claude --plugin-dir ./07-plugins/pr-review

# Checkpoints (auto-enabled, configure in settings)
# See 08-checkpoints/README.md

# Advanced Features (configure in settings)
# See 09-advanced-features/config-examples.json

# CLI Reference (no installation needed)
# See 10-cli/README.md for usage examples

01. Slash Commands

Location: 01-slash-commands/

What: User-invoked shortcuts stored as Markdown files

Examples:

optimize.md - Code optimization analysis
pr.md - Pull request preparation
generate-api-docs.md - API documentation generator

Installation:

cp 01-slash-commands/*.md /path/to/project/.claude/commands/

Usage:

/optimize
/pr
/generate-api-docs

Learn More: Discovering Claude Code Slash Commands

02. Memory

Location: 02-memory/

What: Persistent context across sessions

Examples:

project-CLAUDE.md - Team-wide project standards
directory-api-CLAUDE.md - Directory-specific rules
personal-CLAUDE.md - Personal preferences

Installation:

# Project memory
cp 02-memory/project-CLAUDE.md /path/to/project/CLAUDE.md

# Directory memory
cp 02-memory/directory-api-CLAUDE.md /path/to/project/src/api/CLAUDE.md

# Personal memory
cp 02-memory/personal-CLAUDE.md ~/.claude/CLAUDE.md

Usage: Automatically loaded by Claude

03. Skills

Location: 03-skills/

What: Reusable, auto-invoked capabilities with instructions and scripts

Examples:

code-review-specialist/ - Comprehensive code review with scripts
brand-voice/ - Brand voice consistency checker
doc-generator/ - API documentation generator

Installation:

# Personal skills
cp -r 03-skills/code-review-specialist ~/.claude/skills/

# Project skills
cp -r 03-skills/code-review-specialist /path/to/project/.claude/skills/

Usage: Automatically invoked when relevant

04. Subagents

Location: 04-subagents/

What: Specialized AI assistants with isolated contexts and custom prompts

Examples:

code-reviewer.md - Comprehensive code quality analysis
test-engineer.md - Test strategy and coverage
documentation-writer.md - Technical documentation
secure-reviewer.md - Security-focused review (read-only)
implementation-agent.md - Full feature implementation

Installation:

cp 04-subagents/*.md /path/to/project/.claude/agents/

Usage: Automatically delegated by main agent

05. MCP Protocol

Location: 05-mcp/

What: Model Context Protocol for accessing external tools and APIs

Examples:

github-mcp.json - GitHub integration
database-mcp.json - Database queries (point DATABASE_URL at a SELECT-only user; see read-only setup)
filesystem-mcp.json - File operations
multi-mcp.json - Multiple MCP servers

Installation:

# Set environment variables
export DATABASE_URL="postgresql://..."

# Add MCP server via CLI
claude mcp add --transport http github https://api.githubcopilot.com/mcp/ --header "Authorization: Bearer YOUR_GITHUB_PAT"

# Or add to project .mcp.json manually (see 05-mcp/ for examples)

Usage: MCP tools are automatically available to Claude once configured

06. Hooks

Location: 06-hooks/

What: Event-driven shell commands that execute automatically in response to Claude Code events

Examples:

format-code.sh - Auto-format code after writing
pre-commit.sh - Run tests before commits
security-scan.sh - Scan for security issues
log-bash.sh - Log all bash commands
validate-prompt.sh - Validate user prompts
notify-team.sh - Send notifications on events

Installation:

mkdir -p ~/.claude/hooks
cp 06-hooks/*.sh ~/.claude/hooks/
chmod +x ~/.claude/hooks/*.sh

Configure hooks in ~/.claude/settings.json:

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Write",
        "hooks": [
          { "type": "command", "command": "~/.claude/hooks/format-code.sh" },
          { "type": "command", "command": "~/.claude/hooks/security-scan.sh" }
        ]
      }
    ]
  }
}

Usage: Hooks execute automatically on events

Hook Types (5): command, http, prompt, mcp_tool, agent — how a hook runs.

Hook Events (33, in 4 categories) — when it runs:

Tool Hooks: PreToolUse, PostToolUse, PostToolUseFailure, PostToolBatch, PermissionRequest, PermissionDenied
Session Hooks: SessionStart, Setup, SessionEnd, Stop, StopFailure, SubagentStart, SubagentStop
Task Hooks: UserPromptSubmit, UserPromptExpansion, MessageDisplay, TaskCompleted, TaskCreated, TeammateIdle — TaskCompleted and TaskCreated only fire when the todo tools are enabled, which is available by default only on Claude 3.x models, Opus 4 through 4.7, Sonnet 4 through 4.6, and Haiku 4.5 (CLAUDE_CODE_ENABLE_TODO_TOOLS=1 restores them)
Lifecycle Hooks: ConfigChange, CwdChanged, DirectoryAdded, FileChanged, PreCompact, PostCompact, PreModelSwitch, PostModelSwitch, WorktreeCreate, WorktreeRemove, Notification, InstructionsLoaded, Elicitation, ElicitationResult

07. Plugins

Location: 07-plugins/

What: Bundled collections of commands, agents, MCP, and hooks

Examples:

pr-review/ - Complete PR review workflow
devops-automation/ - Deployment and monitoring
documentation/ - Documentation generation

Installation:

# From the repo root (this repo ships no marketplace, so /plugin install does not apply)
claude --plugin-dir ./07-plugins/pr-review
claude --plugin-dir ./07-plugins/devops-automation
claude --plugin-dir ./07-plugins/documentation

Usage: Use bundled slash commands and features

08. Checkpoints and Rewind

Location: 08-checkpoints/

What: Save conversation state and rewind to previous points to explore different approaches

Key Concepts:

Checkpoint: Snapshot of conversation state
Rewind: Return to previous checkpoint
Branch Point: Explore multiple approaches from same checkpoint

Usage:

# Checkpoints are created automatically with every user prompt
# To rewind, press Esc twice or use:
/rewind

# Then choose from six options:
# 1. Restore code and conversation
# 2. Restore conversation
# 3. Restore code
# 4. Summarize from here
# 5. Summarize up to here
# 6. Never mind

Use Cases:

Try different implementation approaches
Recover from mistakes
Safe experimentation
Compare alternative solutions
A/B testing different designs

09. Advanced Features

Location: 09-advanced-features/

What: Advanced capabilities for complex workflows and automation

Includes:

Planning Mode — Create detailed implementation plans before coding
Extended Thinking — Deep reasoning for complex problems (toggle with Alt+T / Option+T)
Background Tasks — Run long operations without blocking
Permission Modes — manual (config value default), acceptEdits, plan, auto, dontAsk, bypassPermissions
Headless Mode — Run Claude Code in CI/CD: claude -p "Run tests and generate report" --permission-mode auto
Session Management — /resume, /rename, /fork, /branch, claude -c, claude -r
Configuration — Customize behavior in ~/.claude/settings.json

See config-examples.json for complete configurations.

10. CLI Reference

Location: 10-cli/

What: Complete command-line interface reference for Claude Code

Quick Examples:

# Interactive mode
claude "explain this project"

# Print mode (non-interactive)
claude -p "review this code"

# Process file content
cat error.log | claude -p "explain this error"

# JSON output for scripts
claude -p --output-format json "list functions"

# Resume session
claude -r "feature-auth" "continue implementation"

Use Cases: CI/CD pipeline integration, script automation, batch processing, multi-session workflows, custom agent configurations

Example Workflows

Complete Code Review Workflow

# Uses: Slash Commands + Subagents + Memory + MCP

User: /review-pr

Claude:
1. Loads project memory (coding standards)
2. Fetches PR via GitHub MCP
3. Delegates to code-reviewer subagent
4. Delegates to test-engineer subagent
5. Synthesizes findings
6. Provides comprehensive review

Automated Documentation

# Uses: Skills + Subagents + Memory

User: "Generate API documentation for the auth module"

Claude:
1. Loads project memory (doc standards)
2. Detects doc generation request
3. Auto-invokes doc-generator skill
4. Delegates to api-documenter subagent
5. Creates comprehensive docs with examples

DevOps Deployment

# Uses: Plugins + MCP + Hooks

User: /deploy production

Claude:
1. Runs pre-deploy hook (validates environment)
2. Delegates to deployment-specialist subagent
3. Executes deployment via Kubernetes MCP
4. Monitors progress
5. Runs post-deploy hook (health checks)
6. Reports status

Directory Structure

├── 01-slash-commands/
│   ├── optimize.md
│   ├── pr.md
│   ├── generate-api-docs.md
│   └── README.md
├── 02-memory/
│   ├── project-CLAUDE.md
│   ├── directory-api-CLAUDE.md
│   ├── personal-CLAUDE.md
│   └── README.md
├── 03-skills/
│   ├── code-review-specialist/
│   │   ├── SKILL.md
│   │   ├── scripts/
│   │   └── templates/
│   ├── brand-voice/
│   │   ├── SKILL.md
│   │   └── templates/
│   ├── doc-generator/
│   │   ├── SKILL.md
│   │   └── generate-docs.py
│   └── README.md
├── 04-subagents/
│   ├── code-reviewer.md
│   ├── test-engineer.md
│   ├── documentation-writer.md
│   ├── secure-reviewer.md
│   ├── implementation-agent.md
│   └── README.md
├── 05-mcp/
│   ├── github-mcp.json
│   ├── database-mcp.json
│   ├── filesystem-mcp.json
│   ├── multi-mcp.json
│   └── README.md
├── 06-hooks/
│   ├── format-code.sh
│   ├── pre-commit.sh
│   ├── security-scan.sh
│   ├── log-bash.sh
│   ├── validate-prompt.sh
│   ├── notify-team.sh
│   └── README.md
├── 07-plugins/
│   ├── pr-review/
│   ├── devops-automation/
│   ├── documentation/
│   └── README.md
├── 08-checkpoints/
│   ├── checkpoint-examples.md
│   └── README.md
├── 09-advanced-features/
│   ├── config-examples.json
│   ├── planning-mode-examples.md
│   └── README.md
├── 10-cli/
│   └── README.md
└── README.md (this file)

Best Practices

Do's

Start simple with slash commands
Add features incrementally
Use memory for team standards
Test configurations locally first
Document custom implementations
Version control project configurations
Share plugins with team

Don'ts

Don't create redundant features
Don't hardcode credentials
Don't skip documentation
Don't over-complicate simple tasks
Don't ignore security best practices
Don't commit sensitive data

Troubleshooting

Feature Not Loading

Check file location and naming
Verify YAML frontmatter syntax
Check file permissions
Review Claude Code version compatibility

MCP Connection Failed

Verify environment variables
Check MCP server installation
Test credentials
Review network connectivity

Subagent Not Delegating

Check tool permissions
Verify agent description clarity
Review task complexity
Test agent independently

Testing

This project includes comprehensive automated testing:

Unit Tests: Python tests using pytest (Python 3.10, 3.11, 3.12)
Code Quality: Linting and formatting with Ruff
Security: Vulnerability scanning with Bandit
Type Checking: Static type analysis with mypy
Build Verification: EPUB generation testing
Coverage Tracking: Codecov integration

# Install development dependencies
uv pip install -r scripts/requirements-dev.txt

# Run all unit tests
pytest scripts/tests/ -v

# Run tests with coverage report
pytest scripts/tests/ -v --cov=scripts --cov-report=html

# Run code quality checks
ruff check scripts/
ruff format --check scripts/

# Run security scan
bandit -c scripts/pyproject.toml -r scripts/ --exclude scripts/tests/

# Run type checking
mypy scripts/ --ignore-missing-imports

Tests run automatically on every push to main/develop and every PR to main. See TESTING.md for detailed information.

EPUB Generation

Want to read this guide offline? Generate an EPUB ebook:

uv run scripts/build_epub.py

This creates claude-howto-guide.epub with all content, including rendered Mermaid diagrams.

See scripts/README.md for more options.

Contributing

Found an issue or want to contribute an example? We'd love your help!

Please read CONTRIBUTING.md for detailed guidelines on:

Types of contributions (examples, docs, features, bugs, feedback)
How to set up your development environment
Directory structure and how to add content
Writing guidelines and best practices
Commit and PR process

Our Community Standards:

CODE_OF_CONDUCT.md - How we treat each other
SECURITY.md - Security policy and vulnerability reporting

Reporting Security Issues

If you discover a security vulnerability, please report it responsibly:

Use GitHub Private Vulnerability Reporting: https://github.com/luongnv89/claude-howto/security/advisories
Or read .github/SECURITY_REPORTING.md for detailed instructions
Do NOT open a public issue for security vulnerabilities

Quick start:

Fork and clone the repository
Create a descriptive branch (add/feature-name, fix/bug, docs/improvement)
Make your changes following the guidelines
Submit a pull request with a clear description

Need help? Open an issue or discussion, and we'll guide you through the process.

Additional Resources

Claude Code Documentation
MCP Protocol Specification
Skills Repository - Collection of ready-to-use skills
Anthropic Cookbook
Boris Cherny's Claude Code Workflow - The creator of Claude Code shares his systematized workflow: parallel agents, shared CLAUDE.md, Plan mode, slash commands, subagents, and verification hooks for autonomous long-running sessions.

Contributing

We welcome contributions! Please see our Contributing Guide for details on how to get started.

License

MIT License - see LICENSE. Free to use, modify, and distribute. The only requirement is including the license notice.

Last Updated: October 26, 2026 Claude Code Version: 2.1.310 Sources:

Agent Skills 是什么？

Skill 就是一个装着 SKILL.md 的文件夹：头信息写 name 和 description，正文写具体指令；Agent 平时只记描述，匹配请求后再读全文。

快速上手：装第一个 Skill

在技能库挑一条接近任务的 Skill，按详情里的安装说明放到 Agent 目录，用点名或自然语言触发一次并核对结果。

Skills 和 Prompt 怎么选？

只复制一段指令就用 Prompt；要让 Agent 按固定步骤、检查清单或脚本反复完成同一类任务，再用 Skill。

Skills 和 MCP 有什么区别？

Skill 教 Agent 一套做法；MCP 把外部数据和工具接进 Agent。很多工作流两样都要。

按任务挑 Skill，不按名字挑

先写清要完成的事，再在技能库里对 description；再看安装成本、维护状态和权限范围。

典型用途

何时会触发

安装前注意

文件

Lesson Quiz

Prerequisites

Instructions

Step 1: Determine the Lesson

Step 2: Read the Lesson Content

Step 3: Present the Quiz

Step 4: Present Questions in Rounds

Step 5: Score and Present Results

Step 6: Offer Follow-up

Acceptance Criteria

Edge Cases & Error Handling

Invalid lesson argument

User wants to quit mid-quiz

Lesson README not found

Question bank missing entries for a lesson

Validation

Triggering test suite

Master Claude Code in a Weekend

Table of Contents

The Problem

How Claude How To Fixes This

What you get:

How It Works

1. Find your level

2. Follow the guided path

3. Combine features into workflows

4. Test your understanding

Trusted by Developers

Not Sure Where to Start?

Get Started in 15 Minutes

What Can You Build With This?

FAQ

Start Mastering Claude Code Today

Complete Code Review Workflow

Automated Documentation

DevOps Deployment

Do's

Don'ts

Feature Not Loading

MCP Connection Failed

Subagent Not Delegating

Reporting Security Issues

Contributing

License

Agent Skills 是什么？

快速上手：装第一个 Skill

Skills 和 Prompt 怎么选？

Skills 和 MCP 有什么区别？

按任务挑 Skill，不按名字挑

servers

Listing Intelligence Engine

chembl-database

build-review-interface

seo-dataforseo

webnovel-plan

Skill Evolution Manager

feishu-fetch-doc